AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
中文简介正在准备中。当前显示原文说明。
Audit active project plan files for staleness, completion, and routing truth. Use when cleaning up plans, reconciling active work, or archiving completed artifacts.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Output style: Follow
process/development-protocols/communication-standards.md— answer-first, plain language, no unexplained jargon, TL;DR on long responses.
Use this skill to review active plan artifacts and reconcile them with the current codebase.
This is a maintenance and recovery skill, not an automatic post-task hook.
Optional input: a feature, folder, plan filename, or maintenance scope to prioritize.
Prefer it when:
references/audit-plans.md for the full audit process.node .claude/skills/vc-audit-plans/scripts/validate-plan-inventory.mjs
process/general-plans/active/ and process/features/*/active/. Plans now live inside {slug}_{date}/ task subfolders — scan one level deep. Do NOT count _REPORT_, _REF_, or _SPEC_ files inside task folders as plans; only _PLAN_ files count.
For feature-scoped audits, first run find process/features/{feature}/ -type f | sort for full
artifact visibility. For full audits, run find process/features/ -type f | sort to see all
feature artifacts across all subdirs (active, completed, backlog, references, reports).
3.5. Scan task folder contents (co-located REPORT/REF/SPEC files) alongside each plan. Per task-folder artefact colocation, the correct home for every artefact (plan, spec, reports, references) is INSIDE its {slug}_{date}/ task folder; flag any task artefact found in the deprecated sibling reports//references/ dirs or any ad-hoc location as mis-located, and recommend moving it into the owning task folder. Match by feature slug, date proximity (7 days), or content reference to the plan filename.rg searches.Completed, Partially Done, Obsolete, Stale, Active, or Reference.completed/ folder. Use git mv active/{slug}_{date}/ completed/{slug}_{date}/ — move the WHOLE task folder; no completed_ prefix added.Return a concise summary table with classification, action taken, and any user decisions needed. Include stale artifact findings (reports/references tied to completed or obsolete plans) with recommended actions.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
AI-optimized browser automation CLI with context-efficient snapshots. Use for long autonomous sessions, self-verifying workflows, video recording, and cloud browser testing (Browserbase).
中文简介正在准备中。当前显示原文说明。
Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.
中文简介正在准备中。当前显示原文说明。
Audit project context routing, shared-skill discoverability, and Claude/Codex wiring. Use when context docs or skill surfaces move, split, or drift.
中文简介正在准备中。当前显示原文说明。
Audit agent harness health: Claude/Codex agent parity, skill registry consistency, README.md sync, and protocol file wiring. Use when agents, skills, README.md, or development-protocol files move, split, or drift.
中文简介正在准备中。当前显示原文说明。
Emit and validate the provisional goal block for Autopilot Mode. Owns the 9-field format and resume detection from a pasted goal block.
中文简介正在准备中。当前显示原文说明。
Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.
中文简介正在准备中。当前显示原文说明。